Optimization of the Naïve Bayes Classifier Algorithm Using Cost-Sensitive Learning to Detect Lung Diseases with an Imbalanced Dataset

Lung diseases are one of the global public health issues that continue to be a primary concern in the medical field. According to data from the World Health Organization (WHO), 91% of the world’s population lives in areas with poor air quality. Continuous exposure to dust, cigarette smoke, air pollutants, and toxic chemicals can increase the risk of developing lung diseases. In efforts to reduce the health impacts on the lungs and assist doctors in classifying lung diseases, a method is needed to predict lung diseases. Naïve Bayes is a classification technique that uses probability and statistics. This research uses a dataset of 30,000, which is divided into training data and testing data, with 80% allocated for training and 20% for testing. The results of this study show that optimization performed on the Naïve Bayes algorithm using cost-sensitive learning achieved an accuracy of 79.6%, which represents a 12% improvement in accuracy compared to the previous result without optimization.